Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12525
    Prev
    Next
    INDEX
    Explanations

    terms related to minimization and optimization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.71
    IntoConstraints
    -0.65
    Халык
    -0.63
    enumi
    -0.63
     Савезне
    -0.62
     GenerationType
    -0.61
    /******/
    -0.60
    
    -0.60
    Билгалдахарш
    -0.59
    ionario
    -0.58
    POSITIVE LOGITS
    ized
    1.59
    ization
    1.59
    izing
    1.57
    isation
    1.57
    ising
    1.45
    ize
    1.42
    ised
    1.39
    izes
    1.39
    izer
    1.35
    IZED
    1.28
    Activations Density 0.446%

    No Known Activations